Comments (11)
yifanfeng97
commented on June 12, 2024
从严谨的角度来讲，这里你提的问题是对的，确实D_v应该多乘上一个W。我这里因为目前处理的都是等权超边的超图，所以实现D_v的时候只对H的列做了sum，并没有乘上W。我会在下个版本修复这个bug，或者你也可以尝试提交pull request哦！
from deephypergraph.
liuzhh1998
commented on June 12, 2024
感谢！请问下个版本什么时候能发布呢
刘志航
***@***.***
…------------------ 原始邮件 ------------------
发件人: "iMoonLab/DeepHypergraph" ***@***.***>;
发送时间: 2022年12月19日(星期一) 下午4:09
***@***.***>;
***@***.******@***.***>;
主题: Re: [iMoonLab/DeepHypergraph] 超图的顶点度矩阵D_v (Issue #25)
从严谨的角度来讲，这里你提的问题是对的，确实D_v应该多乘上一个W。我这里因为目前处理的都是等权超边的超图，所以实现D_v的时候只对H的列做了sum，并没有乘上W。我会在下个版本修复这个bug，或者你也可以尝试提交pull request哦！
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
from deephypergraph.
yifanfeng97
commented on June 12, 2024
预计一周内会发一个新版本，你还有没有一些其他的需求？我可以顺便都加上
from deephypergraph.
liuzhh1998
commented on June 12, 2024
在部分实际应用中，超图的属性中还包括顶点的权重，比如在超图划分领域。用dhg创建超图，目前应该不能设置顶点的权重。如果可以的话，可以将这个功能加上。
万分感谢！！！
刘志航
***@***.***
…------------------ 原始邮件 ------------------
发件人: "iMoonLab/DeepHypergraph" ***@***.***>;
发送时间: 2022年12月19日(星期一) 晚上7:06
***@***.***>;
***@***.******@***.***>;
主题: Re: [iMoonLab/DeepHypergraph] 超图的顶点度矩阵D_v (Issue #25)
预计一周内会发一个新版本，你还有没有一些其他的需求？我可以顺便都加上
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
from deephypergraph.
yifanfeng97
commented on June 12, 2024
好，在实际的超图的抽象类里面，我已经增加了顶点权重，原本计划后续版本再把顶点权重放出来。我可以在下个版本提前增加顶点权重到无向超图类里面！
from deephypergraph.
yifanfeng97
commented on June 12, 2024
Reference in
Fix in 7786e2d .
hg = dhg.Hypergraph(5, [(0, 1, 2), (2, 3), (0, 4)], [2.0, 3.0, 4.0])
最新main分支中dhg中计算得到的D_v为 ：
tensor([[6., 0., 0., 0., 0.],
[0., 2., 0., 0., 0.],
[0., 0., 5., 0., 0.],
[0., 0., 0., 3., 0.],
[0., 0., 0., 0., 4.]])
from deephypergraph.
yifanfeng97
commented on June 12, 2024
方便的话，可以star一下哦！
from deephypergraph.
yifanfeng97
commented on June 12, 2024
在 e17fc95 增加了 v_weight
在超图构建的时候传入参数v_weight即可初始化节点权重
W_v : https://deephypergraph.readthedocs.io/en/latest/api/dhg.html#dhg.Hypergraph.W_v
这个新特性预计这两天随着dhg 0.9.3 一起发布
from deephypergraph.
yifanfeng97
commented on June 12, 2024
已发布 0.9.3 https://pypi.org/project/dhg/
可以直接pip install dhg 来安装0.9.3啦
from deephypergraph.
liuzhh1998
commented on June 12, 2024
好嘞
刘志航
***@***.***
…------------------ 原始邮件 ------------------
发件人: "iMoonLab/DeepHypergraph" ***@***.***>;
发送时间: 2022年12月27日(星期二) 下午4:08
***@***.***>;
***@***.******@***.***>;
主题: Re: [iMoonLab/DeepHypergraph] 超图的顶点度矩阵D_v (Issue #25)
已发布 0.9.3 https://pypi.org/project/dhg/
可以直接pip install dhg 来安装0.9.3啦
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
from deephypergraph.
yifanfeng97
commented on June 12, 2024
合并到 https://github.com/iMoonLab/DeepHypergraph/releases/tag/v0.9.3
from deephypergraph.
Related Issues (20)
- 如何利用DHG实现整图分类任务 HOT 4
- About Directed Hypergraph HOT 3
- adaptive fusion和coequal fusion的文档问题 HOT 2
- How to use HGNN+ for RL
- mini-batches training for node classification on hypergraph
- Unable to install dhg using pip HOT 2
- CoauthorshipCora dataset label error HOT 1
- 请帮忙看一下画图代码draw_hypergraph（）的参数无法调整如v_line_width和e_line_width，限制输入的格式错了，修改也没变化。 HOT 2
- 我针对你的超图写了个邻接矩阵的接口，想请老哥帮忙看看写的对不对？我自己也做了个些测试，输出的挺对，你介意合并不？ HOT 2
- 中文文档有误
- 大型图的处理
- torch.topk 函数设置 largest=False 是为了找到最小的距离，即最近的邻居。这种方法可能比转换张量为 numpy 数组并使用 scipy.spatial.cKDTree 更有效，因为它避免了 CPU 和 GPU 之间的数据传输。 HOT 1
- 如何获取训练后节点的向量？
- e_weight=None，agg='softmax' 时Graph类v2v中x=torch.sparse.mm(P,dim=1)应该是x=torch.sparse.softmax(P,dim=1)
- Didn't concat node's vector with hyperedge's vector before computing the attention of UniGATConv
- How to get a directed hypergraph HOT 2
- 超图实现具有不同超边权重的超图卷积模型
- 关于UniGCN在计算超边的度的平均值，这是否是一个bug
- 您好在使用dhg.models.HGNN出现torch.sparse_coo_tensor的索引超出我的张量尺寸范围，具体的bug如下 HOT 1
- Can we generate a corresponding hypergraph dataset based on a real-world GNN graph embedding dataset?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from deephypergraph.